personal_edge

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral disclosure burden. It reveals a concrete rule: the tool refuses to issue a raise/lower verdict until a group has at least min_sample measured decisions. It also scopes results to 'measured rows', which is useful beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact: two sentences with the core distinction front-loaded and the behavioral rule stated efficiently. The phrasing 'evidence threshold raise/lower' is somewhat jargon-heavy, but the entry as a whole is informative without being bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, it does state the main metrics returned and a key guardrail. However, it leaves min_days unexplained and does not clarify behavior when there are no measured decisions for a category. These are material gaps for an agent deciding how to call and interpret the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema describes min_sample but not min_days, leaving schema coverage at 50%. The description reinforces min_sample's role in the refusal behavior and mentions its default, but it adds no meaning for min_days. Since schema coverage is low, the description should compensate for the missing parameter semantics, and it does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's output: the user's own decision track record, consisting of mean decision alpha and hit rate by category/theme. It explicitly contrasts with 'a market study', which helps orient the agent, though it does not name or differentiate specific sibling tools like decision_quality or review_decisions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives contextual guidance by saying this is the user's personal track record rather than a market study, and it points to log_decision's category/theme fields. However, it does not explicitly state when to use this tool versus alternatives such as decision_quality or review_decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.